Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Database Concurrency Optimizations #80

Merged
merged 3 commits into from
Dec 13, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](http://semver.org/).

## [0.0.15]

### Added

- Alembic for handling database migrations
- Additional indexes for reading Messages and Metamessages

### Fixed

- Dialectic Streaming Endpoint properly sends text in `StreamingResponse`
Expand Down
117 changes: 117 additions & 0 deletions alembic.ini
Original file line number Diff line number Diff line change
@@ -0,0 +1,117 @@
# A generic, single database configuration.

[alembic]
# path to migration scripts
# Use forward slashes (/) also on windows to provide an os agnostic path
script_location = migrations

# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
# Uncomment the line below if you want the files to be prepended with date and time
# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
# for all available tokens
# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s

# sys.path path, will be prepended to sys.path if present.
# defaults to the current working directory.
prepend_sys_path = .

# timezone to use when rendering the date within the migration file
# as well as the filename.
# If specified, requires the python>=3.9 or backports.zoneinfo library.
# Any required deps can installed by adding `alembic[tz]` to the pip requirements
# string value is passed to ZoneInfo()
# leave blank for localtime
# timezone =

# max length of characters to apply to the "slug" field
# truncate_slug_length = 40

# set to 'true' to run the environment during
# the 'revision' command, regardless of autogenerate
# revision_environment = false

# set to 'true' to allow .pyc and .pyo files without
# a source .py file to be detected as revisions in the
# versions/ directory
# sourceless = false

# version location specification; This defaults
# to migrations/versions. When using multiple version
# directories, initial revisions must be specified with --version-path.
# The path separator used here should be the separator specified by "version_path_separator" below.
# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions

# version path separator; As mentioned above, this is the character used to split
# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
# Valid values for version_path_separator are:
#
# version_path_separator = :
# version_path_separator = ;
# version_path_separator = space
# version_path_separator = newline
version_path_separator = os # Use os.pathsep. Default configuration used for new projects.

# set to 'true' to search source files recursively
# in each "version_locations" directory
# new in Alembic version 1.10
# recursive_version_locations = false

# the output encoding used when revision files
# are written from script.py.mako
# output_encoding = utf-8

sqlalchemy.url = driver://user:pass@localhost/dbname


[post_write_hooks]
# post_write_hooks defines scripts or Python functions that are run
# on newly generated revision scripts. See the documentation for further
# detail and examples

# format using "black" - use the console_scripts runner, against the "black" entrypoint
# hooks = black
# black.type = console_scripts
# black.entrypoint = black
# black.options = -l 79 REVISION_SCRIPT_FILENAME

# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
# hooks = ruff
# ruff.type = exec
# ruff.executable = %(here)s/.venv/bin/ruff
# ruff.options = --fix REVISION_SCRIPT_FILENAME

# Logging configuration
[loggers]
keys = root,sqlalchemy,alembic

[handlers]
keys = console

[formatters]
keys = generic

[logger_root]
level = WARNING
handlers = console
qualname =

[logger_sqlalchemy]
level = WARNING
handlers =
qualname = sqlalchemy.engine

[logger_alembic]
level = INFO
handlers =
qualname = alembic

[handler_console]
class = StreamHandler
args = (sys.stderr,)
level = NOTSET
formatter = generic

[formatter_generic]
format = %(levelname)-5.5s [%(name)s] %(message)s
datefmt = %H:%M:%S
6 changes: 3 additions & 3 deletions fly.toml
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,13 @@ kill_timeout = '5s'
internal_port = 8000
auto_stop_machines = 'off'
auto_start_machines = true
min_machines_running = 1
min_machines_running = 3
processes = ['api']

[http_service.concurrency]
type = 'requests'
hard_limit = 250
soft_limit = 200
hard_limit = 50
soft_limit = 20

[[vm]]
memory = '512mb'
Expand Down
1 change: 1 addition & 0 deletions migrations/README
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Generic single-database configuration.
95 changes: 95 additions & 0 deletions migrations/env.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
import os
import sys
from logging.config import fileConfig
from pathlib import Path

from alembic import context
from dotenv import load_dotenv
from sqlalchemy import engine_from_config, pool

# Import your models
from src.db import Base

# Add project root to Python path
sys.path.append(str(Path(__file__).parents[1]))

# Load environment variables
load_dotenv()

# this is the Alembic Config object, which provides
# access to the values within the .ini file in use.
config = context.config

# Interpret the config file for Python logging.
# This line sets up loggers basically.
if config.config_file_name is not None:
fileConfig(config.config_file_name, disable_existing_loggers=False)

# add your model's MetaData object here
# for 'autogenerate' support
# from myapp import mymodel
# target_metadata = mymodel.Base.metadata
target_metadata = Base.metadata

# other values from the config, defined by the needs of env.py,
# can be acquired:
# my_important_option = config.get_main_option("my_important_option")
# ... etc.


def get_url():
return os.getenv("CONNECTION_URI")


def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode.

This configures the context with just a URL
and not an Engine, though an Engine is acceptable
here as well. By skipping the Engine creation
we don't even need a DBAPI to be available.

Calls to context.execute() here emit the given string to the
script output.

"""
# url = config.get_main_option("sqlalchemy.url")
url = get_url()
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
)

with context.begin_transaction():
context.run_migrations()


def run_migrations_online() -> None:
"""Run migrations in 'online' mode.

In this scenario we need to create an Engine
and associate a connection with the context.

"""
configuration = config.get_section(config.config_ini_section)
configuration["sqlalchemy.url"] = get_url()

connectable = engine_from_config(
configuration,
prefix="sqlalchemy.",
poolclass=pool.NullPool,
)

with connectable.connect() as connection:
context.configure(connection=connection, target_metadata=target_metadata)

with context.begin_transaction():
context.run_migrations()


if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
26 changes: 26 additions & 0 deletions migrations/script.py.mako
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
"""${message}

Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}

"""
from typing import Sequence, Union

from alembic import op
import sqlalchemy as sa
${imports if imports else ""}

# revision identifiers, used by Alembic.
revision: str = ${repr(up_revision)}
down_revision: Union[str, None] = ${repr(down_revision)}
branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}


def upgrade() -> None:
${upgrades if upgrades else "pass"}


def downgrade() -> None:
${downgrades if downgrades else "pass"}
60 changes: 60 additions & 0 deletions migrations/versions/c3828084f472_add_indexes_for_messages_and_.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
"""Add indexes for messages and metamessages for reads

Revision ID: c3828084f472
Revises:
Create Date: 2024-12-12 13:41:40.156095

"""

from typing import Sequence, Union

import sqlalchemy as sa
from sqlalchemy import text
from alembic import op
from sqlalchemy.dialects import postgresql

# revision identifiers, used by Alembic.
revision: str = "c3828084f472"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
# Add new indexes
op.create_index("idx_users_app_lookup", "users", ["app_id", "public_id"])
op.create_index("idx_sessions_user_lookup", "sessions", ["user_id", "public_id"])

op.create_index(
"idx_messages_session_lookup",
"messages",
["session_id", "id"],
postgresql_include=[
"public_id",
"is_user",
"content",
"metadata",
"created_at",
],
)

op.create_index(
"idx_metamessages_lookup",
"metamessages",
["metamessage_type", sa.text("id DESC")],
postgresql_include=[
"public_id",
"content",
"message_id",
"created_at",
"metadata",
],
)


def downgrade() -> None:
# Remove new indexes
op.drop_index("idx_users_app_lookup", table_name="users")
op.drop_index("idx_sessions_user_lookup", table_name="sessions")
op.drop_index("idx_messages_session_lookup", table_name="messages")
op.drop_index("idx_metamessages_lookup", table_name="metamessages")
3 changes: 2 additions & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,15 @@ dependencies = [
"sqlalchemy>=2.0.30",
"fastapi-pagination>=0.12.24",
"pgvector>=0.2.5",
"sentry-sdk[fastapi,sqlalchemy]>=2.3.1",
"sentry-sdk[fastapi,sqlalchemy,anthropic]>=2.3.1",
"greenlet>=3.0.3",
"psycopg[binary]>=3.1.19",
"httpx>=0.27.0",
"rich>=13.7.1",
"openai>=1.43.0",
"anthropic>=0.36.0",
"nanoid>=2.0.0",
"alembic>=1.14.0",
]
[tool.uv]
dev-dependencies = [
Expand Down
Loading
Loading